slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
Provides a single, OpenAI-compatible endpoint to access multiple free LLM providers, with automatic updates and a lightweight, zero-dependency design.
Who it is for
- Developers who use free LLM APIs from multiple providers
- AI agent builders needing a unified proxy
- Self-hosters seeking a minimal setup for model aggregation
- Users who want to share free models across multiple agents
Use cases
- Run a local API gateway to switch between free models without changing agent configs
- Automate periodic refresh of available free models from providers
- Manage providers and models through a web dashboard
- Enable Pi agents to automatically discover free models
Strengths
- Simple one-command install and startup
- Zero-dependency web UI using Python stdlib
- Automatic model refresh every 12 hours
- Pluggable provider sources for easy extension
- MIT license for open use
Considerations
- Relies on the availability and stability of each provider's free tier
- Requires users to obtain API keys for each provider
- Currently only supports the 9 listed providers; adding new ones requires custom code
- Test coverage is 22 tests, which may not cover all edge cases
README quick start
安装
Description
免费的LLM模型路由器、代理和同步引擎。Free LLM model router, proxy, and sync engine.
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.